GraySoft
Projects Models Compare Cloud benchmarks FAQ Download guIDE →
Model Intelligence Sheet

kernelpool/MiMo-V2.6-Flash-MOPD-MXFP4-GGUF overview

MiMo V2.6 Flash MOPD GGUF for DwarfStar GGUF files for the MiMo V2.6 Flash port in DwarfStar DS4 https://github.com/antirez/ds4 , branch kernelpool/ds4:mimo v2…

ggufmimometalbase_model:XiaomiMiMo/MiMo-V2.6-Flash-MOPDbase_model:quantized:XiaomiMiMo/MiMo-V2.6-Flash-MOPDlicense:mitendpoints_compatibleregion:usconversational

Runs locally from ~739.7 MB disk (4 GB VRAM class GPUs with llama.cpp / guIDE).

Downloads
367
Likes
1
Pipeline
—

Repository Files & Downloads

4 GGUF files detected
Direct downloads for local inference
FileTypeQuantizationSizeLink
MiMo-V2.6-Flash-MOPD-DFlash-Q8_0.ggufGGUFQ8_01.45 GBDownload
MiMo-V2.6-Flash-MOPD-MXFP4.ggufGGUFGGUF157.40 GBDownload
MiMo-V2.6-Flash-MOPD-Vision-F32.ggufGGUFF322.71 GBDownload
MiMo-V2.6-Flash-MOPD-Vision-Q8_0.ggufGGUFQ8_0739.7 MBDownload

Model Details

Model IDkernelpool/MiMo-V2.6-Flash-MOPD-MXFP4-GGUF
Authorkernelpool
Pipeline—
Licensemit
Base modelXiaomiMiMo/MiMo-V2.6-Flash-MOPD
Last modified2026-10-04T03:08:13.000Z

Model README

---

license: mit

base_model: XiaomiMiMo/MiMo-V2.6-Flash-MOPD

tags:

  • gguf
  • mimo
  • metal

---

MiMo-V2.6 Flash MOPD GGUF for DwarfStar

GGUF files for the MiMo-V2.6 Flash port in DwarfStar (DS4),

branch kernelpool/ds4:mimo-v26

(pull request: TODO link). Metal only.

MOPD is Xiaomi's update of the MiMo-V2.6 Flash RL checkpoint that reduces

repeated tool calls in agent sessions

(Xiaomi's write-up).

Only the main model changed: the MTP blocks, the DFlash drafter and the vision

tower carry the same weights as the RL release. The files below replace

kernelpool/MiMo-V2.6-Flash-MXFP4-GGUF

and use the same layout. Requantized Q4 and Q2 files of the same checkpoint

are in kernelpool/MiMo-V2.6-Flash-MOPD-GGUF.

| File | Size | Content |

| --- | ---: | --- |

| MiMo-V2.6-Flash-MOPD-MXFP4.gguf | 157.4 GiB | Main model, mimo2 layout: the checkpoint's own MXFP4 experts repacked without requantization, Q8_0 attention, dense and output weights, BF16 embeddings, the three MTP blocks |

| MiMo-V2.6-Flash-MOPD-DFlash-Q8_0.gguf | 1.5 GiB | DFlash drafter sidecar, dflash layout plus the mask embedding and value scale DS4 needs |

| MiMo-V2.6-Flash-MOPD-Vision-F32.gguf | 2.7 GiB | Vision encoder, lossless (recommended) |

| MiMo-V2.6-Flash-MOPD-Vision-Q8_0.gguf | 0.7 GiB | Vision encoder, Q8_0 matrices, smaller and measurably less exact |

Run

git clone -b mimo-v26 https://github.com/kernelpool/ds4 && cd ds4 && make
./ds4 -m MiMo-V2.6-Flash-MOPD-MXFP4.gguf --mtp
./ds4 -m MiMo-V2.6-Flash-MOPD-MXFP4.gguf --mtp --vision MiMo-V2.6-Flash-MOPD-Vision-F32.gguf
./ds4-server -m MiMo-V2.6-Flash-MOPD-MXFP4.gguf --mtp --vision MiMo-V2.6-Flash-MOPD-Vision-F32.gguf

--mtp drafts with the MTP blocks inside the main file and is the faster

option; --mtp-model MiMo-V2.6-Flash-MOPD-DFlash-Q8_0.gguf uses the DFlash

sidecar instead. Both verify against the target, so temperature-zero output

follows plain decoding. The main file needs a 192 GB or larger Mac.

See docs/MIMO_V26.md.

Conversion

Written by gguf-tools/mimo26_quantize.py and gguf-tools/mimo26_vision.py

from XiaomiMiMo/MiMo-V2.6-Flash-MOPD at revision

2479e2d0029eca9a34cc7e7f55a121925f81908e. The converter de-interleaves the

tensor-parallel chunks of the fused QKV projection and keeps the released

MXFP4 expert blocks bit for bit; the source revision is recorded in the

GGUF metadata.

Quality

Scored on 100 official continuations from the Xiaomi platform with the

fixture in gguf-tools/quality-testing/mimo-v2.6-flash-20260922; the MOPD

file scores on par with the RL release there.

The vision encoder reproduces the checkpoint's tower on identical inputs.

The original checkpoint is released by Xiaomi under the MIT license, which

applies to these files as well.

Run kernelpool/MiMo-V2.6-Flash-MOPD-MXFP4-GGUF with guIDE

Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.

Download guIDE → · Browse 524k+ models · Compare models

Source: Hugging Face · Compare models